Our paper has been accepted to the Workshop on Ubiquitous Network Intelligence for Next Generation Wireless Networks in IEEE GLOBECOM 2024). This work is collaborative research with Prof. Nishio at Tokyo Institute of Technology. This paper proposes neural architectures with vector quantized bottlenecks for split inference to reduce the traffic between edge devices and servers.

Our paper has been accepted to 31st International Conference on Neural Information Processing (ICONIP 2024). This paper proposes an adaptation method of trust region for trust region policy optimization (TRPO).

• Shoma Shimizu, Kento Uchida, Atsuo Maki, and Shinichi Shirakawa: Adaptive Trust Region Radius for Robust Policy Optimization, 31st International Conference on Neural Information Processing (ICONIP 2024), Auckland, New Zealand, December 2-6, 2024.

Our paper regarding theoretical analysis for the categorical version of the compact genetic algorithm has been accepted to Evolutionary Computation (MIT Press). This work is collaborative research with Prof. Akimoto (University of Tsukuba), etc.

• Ryoki Hamano, Kento Uchida, Shinichi Shirakawa, Daiki Morinaga, and Youhei Akimoto: Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm, Evolutionary Computation, (Accepted) [DOI] [arXiv]

Three papers have been accepted to Parallel Problem Solving from Nature (PPSN 2024).

Our paper regarding LLM for automated feature engineering has been accepted to AutoML Conference 2024 Workshop Track.

• Yoichi Hirose, Kento Uchida, and Shinichi Shirakawa, Fine-Tuning LLMs for Automated Feature Engineering, International Conference on Automated Machine Learning (AutoML Conference) 2024 Workshop Track, Paris, France, September 9-12, 2024. [Link]

Our papers (three full papers and one poster paper) have been accepted to Genetic and Evolutionary Computation Conference (GECCO) 2024.

Our papers regarding search space design for NAS and open domain generalization have been accepted to International Joint Conference on Neural Networks (IJCNN 2024) (Part of WCCI 2024) held in Yokohama.

Our paper has been accepted to Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2024). This paper introduces the feature selection mechanism into Neural Additive Models and Neural Basis Models, which are interpretable machine learning models, and enables them to apply high-dimensional datasets.

Members’ Page has been updated. Now, our laboratory has 8 doctoral course students, 14 master’s course students, and 6 undergraduate students for graduation research.

Our paper regarding the conversion of tabular data to image data has been accepted to Knowledge-Based Systems.

• Takuya Matsuda, Kento Uchida, Shota Saito, and Shinichi Shirakawa: HACNet: End-to-end learning of interpretable table-to-image converter and convolutional neural network, Knowledge-Based Systems, Vol. 284, 111293, Jan. 2024. [DOI]